2.0.1

What's Changed

• Merge 2.0.1 release changes by @rahuldshetty in #13

• Structured LLM output with JSON Schema and GBNF Grammar Support for model type 'GGUF_CPU'

Full Changelog: 2.0.0...2.0.1

2.0.0

What's Changed

• Bump @babel/traverse from 7.22.8 to 7.23.4 by @dependabot in #2
• Enable Model Caching by @rahuldshetty in #4
• Use the Browser's Cache Storage if it's available, to avoid re-downloading models by @felladrin in #3
• Initial Release of 2.0.0 version by @rahuldshetty in #12

New Contributors

• @dependabot made their first contribution in #2
• @felladrin made their first contribution in #3

Full Changelog: 1.0.2...2.0.0

1.0.2

Added

• Latest GGUF format supported with latest updated llama2-cpp module.
• Added context_size parameter for llama models.

Changed

• Rebranded project to "LLM.JS".
• Removed STACK_SIZE flag from build scripts.

1.0.1

Added

• Added support for llama2.c models

Changed

• Added tokenizer_url parameter in GGML Wrapper for supporting LLaMa2.
• Upgraded ggml version to 244776a

1.0.0

Added

• ggml.js package
• Added Model Support for Dollyv2, GPT2, GPT J, GPT Neo X, MPT, Replit, StarCoder
• docsify documentation